General Principles
APA statistical reporting follows these principles:
- Report exact p-values to two or three decimal places (p = .023), unless p < .001.
- Italicise statistical symbols (t, F, r, p, M, SD) but not Greek letters (χ², β, α).
- Use spaces around mathematical operators (M = 3.45, not M=3.45).
- Round appropriately — p-values to two or three decimal places, test statistics to two, effect sizes to two.
- Report effect sizes alongside every significance test.
- Report confidence intervals where appropriate, especially for primary outcomes.
Descriptive Statistics
Always report descriptive statistics before inferential tests:
- Means and standard deviations: Children in the intervention group scored higher (M = 4.32, SD = 1.05) than those in the control group (M = 3.78, SD = 0.98).
- Medians and interquartile ranges for non-normally distributed data: Median response time was 2.3 s (IQR = 1.8–3.1).
- Frequencies and percentages for categorical data: Of the 200 participants, 120 (60%) were female.
t-Tests
Independent samples t-test:
An independent-samples t-test showed that the intervention group scored significantly higher than the control group, t(98) = 2.74, p = .007, d = 0.55.
Paired samples t-test:
Anxiety scores decreased significantly from pre-test (M = 28.4, SD = 6.2) to post-test (M = 22.1, SD = 5.8), t(49) = 5.82, p < .001, d = 0.82.
Key elements: test statistic, degrees of freedom, p-value, effect size.
ANOVA
One-way ANOVA:
A one-way ANOVA revealed a significant effect of teaching method on exam scores, F(2, 87) = 4.23, p = .018, η² = .09. Post-hoc comparisons using Tukey's HSD indicated that the active learning group (M = 76.3, SD = 8.4) scored significantly higher than the lecture group (M = 68.1, SD = 9.2, p = .014), but not significantly higher than the blended group (M = 72.5, SD = 8.9, p = .121).
Factorial ANOVA:
There was a significant interaction between teaching method and prior achievement, F(2, 84) = 3.67, p = .030, partial η² = .08.
Key elements: F-statistic, degrees of freedom (between, within), p-value, effect size (η² or partial η²), and post-hoc tests if significant.
Correlation
Pearson correlation:
There was a significant positive correlation between study hours and exam scores, r(98) = .42, p < .001. The coefficient of determination indicated that study hours explained 17.6% of the variance in exam scores.
Spearman correlation (for non-parametric data):
A Spearman rank-order correlation showed a significant relationship between class rank and motivation score, rₛ(48) = .35, p = .014.
Regression
Simple linear regression:
Study hours significantly predicted exam scores, β = .42, t(98) = 4.67, p < .001. The model explained 18.2% of the variance (R² = .18, F(1, 98) = 21.84, p < .001).
Multiple regression:
Study hours and sleep quality together predicted 31% of the variance in exam scores (R² = .31, F(2, 97) = 21.84, p < .001). After controlling for sleep quality, study hours remained a significant predictor (β = .34, p < .001), while sleep quality was also significant (β = .22, p = .018).
Report β (standardised coefficient) or b (unstandardised), t, p, and R² for the model. Report change in R² if adding predictors in steps.
Chi-Square
Chi-square test of independence:
A chi-square test of independence revealed a significant association between treatment group and recovery status, χ²(1, N = 200) = 8.45, p = .004, Cramér's V = .21. Participants in the treatment group were 1.8 times more likely to recover than those in the control group (OR = 1.80, 95% CI [1.21, 2.68]).
Key elements: χ² value, degrees of freedom, sample size, p-value, effect size (Cramér's V or φ), and odds ratio with confidence interval for 2×2 tables.
Confidence Intervals
APA style encourages reporting confidence intervals, especially for primary outcomes:
The mean difference between groups was 4.56 points (95% CI [1.87, 7.25]), indicating that the true population difference is likely between 1.87 and 7.25 points.
Tables and Figures
- Number tables and figures sequentially (Table 1, Table 2, Figure 1, Figure 2).
- Use italic titles above tables and below figures.
- Report exact p-values in tables, not asterisks alone.
- Include effect sizes in every table that reports significance tests.
- Use horizontal rules only (no vertical lines) in APA-style tables.
Need Help With Your Results Chapter?
We can format your statistical results in APA style, create publication-ready tables and figures, and write your results chapter. Get in touch for a free consultation.
[Get Help With APA Formatting → /for-students/dissertation-help/results-chapter-writing/]
[Contact Us → /contact/]